CodeGate: Security, Workspaces and Multiplexing for AI Agentic Frameworks

Here Comes the AI Worm: Preventing the Propagation of Adversarial Self-Replicating Prompts Within GenAI Ecosystems

CTF challenges designed and implemented in machine learning applications

An interactive CLI application for interacting with authenticated Jupyter instances.

A collection list for Large Language Model (LLM) Watermark

Powerful LLM Query Framework with YAML Prompt Templates. Made for Automation

CyberBrain_Model is an advanced AI project designed for fine-tuning the model `DeepSeek-R1-Distill-Qwen-14B` specifically for cyber security tasks.

[COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model

🤯 AI Security EXPOSED! Live Demos Showing Hidden Risks of 🤖 Agentic AI Flows: 💉Prompt Injection, ☣️ Data Poisoning. Watch the recorded session:

AI runtime inventory: discover shadow AI, trace LLM calls

Securing LLM's Against Top 10 OWASP Large Language Model Vulnerabilities 2024

This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms." ASSET achieves state-of-the-art reliability in detecting poisoned samples in end-to-end supervised learning/ self-supervised learning/ transfer learning.

A distributed honeypot for monitoring large scale web attacks

It is a pure front-end tool for testing the security boundaries of large language models, helping researchers to find and fix potential security vulnerabilities and improve the security and reliability of AI systems.

CyberBrain is an advanced AI project designed specifically for training artificial intelligence models on devices with limited hardware capabilities.

利用Ai对靶场进行自动化高效完成渗透测试！

AI Red Team & Blue Team Tips & Tricks!

This repository demonstrates a variety of **MCP Poisoning Attacks** affecting real-world AI agent workflows.

This repo contains reference implementations, tutorials, samples, and documentation for working with Bosch AIShield

LLM Security Project with Llama Guard